✨ About The Role
- Responsible for pioneering methodologies and implementing systems to integrate human feedback into AI models and systems
- Design and implement systems for collecting and integrating high-quality human feedback into AI systems
- Explore ways to use various forms of human feedback to benefit model training
- Study human-AI collaboration for challenging tasks, including those in sensitive or regulated domains
- Contribute to the development of tooling and workflow for offline iteration and feedback integration
âš¡ Requirements
- Experienced individual with a strong passion for OpenAI's mission of building safe, universally beneficial AGI
- Holds a Ph.D. or other degree in computer science, machine learning, or a related field
- Demonstrates 3+ years of experience in AI safety, particularly in areas like RLHF, human-AI collaboration, and human feedback collection
- Possesses an in-depth understanding of deep learning research and/or strong engineering skills
- Goal-oriented mindset, willing to engage in high-value work even if it is tedious